{"total":35,"rows":[{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2509.13281","title":"RepIt: Steering Language Models with Concept-Specific Refusal Vectors","created":"2025-09-16","cited_by_count":12,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2605.05715","title":"Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2601.01584","title":"Steerability of Instrumental-Convergence Tendencies in LLMs","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2602.16980","title":"Discovering Universal Activation Directions for PII Leakage in Language Models","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2604.11120","title":"Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.17778","title":"Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.27169","title":"Semantic Structure of Feature Space in Large Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.24583","title":"Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.26161","title":"Refusal Lives Downstream of Persona in Chat Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.28843","title":"The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.01859","title":"Safety Targeted Embedding Exploit via Refinement","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05356","title":"ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.15772","title":"Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.17836","title":"Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.21928","title":"GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.29109","title":"Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.10142","title":"Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.22224","title":"From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22260","title":"Causal Localization of the Refusal Direction in Audio Language Models","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.27158","title":"The Linear Representation Hypothesis Needs a Group Action","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35117","title":"Tool Mediation Alters Refusal Mechanisms in Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37659","title":"Are In-Context Images Worth 10 Dimensions?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04183","title":"Language Model Activations Inhabit Privileged Error-Correcting Basins","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07270","title":"Does the Model Use the Feature? Separating Steering from Mechanism in LLMs","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}